Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4360 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.5351. Min Act: -0.0001

Data Index: 832683 (C4 (Web Text))

Max Activating Token Index: 814

Text #1

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.3568. Min Act: -0.0001

Data Index: 527621 (C4 (Web Text))

Max Activating Token Index: 423

Text #2

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.0834. Min Act: -0.0001

Data Index: 718270 (C4 (Web Text))

Max Activating Token Index: 158

Text #3

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1441. Min Act: -0.0001

Data Index: 760587 (C4 (Web Text))

Max Activating Token Index: 417

Text #4

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.2785. Min Act: -0.0001

Data Index: 411897 (C4 (Web Text))

Max Activating Token Index: 667

Text #5

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1963. Min Act: -0.0001

Data Index: 510658 (C4 (Web Text))

Max Activating Token Index: 868

Text #6

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1727. Min Act: -0.0001

Data Index: 661812 (C4 (Web Text))

Max Activating Token Index: 4

Text #7

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.2664. Min Act: -0.0001

Data Index: 559039 (C4 (Web Text))

Max Activating Token Index: 134

Text #8

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.0689. Min Act: -0.0001

Data Index: 443643 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1151. Min Act: -0.0001

Data Index: 273538 (C4 (Web Text))

Max Activating Token Index: 691

Text #10

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.2777. Min Act: -0.0001

Data Index: 698617 (C4 (Web Text))

Max Activating Token Index: 1009

Text #11

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.3718. Min Act: -0.0001

Data Index: 800671 (C4 (Web Text))

Max Activating Token Index: 794

Text #12

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1916. Min Act: -0.0001

Data Index: 1117408 (C4 (Web Text))

Max Activating Token Index: 106

Text #13

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1185. Min Act: -0.0001

Data Index: 104375 (C4 (Web Text))

Max Activating Token Index: 442

Text #14

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1377. Min Act: -0.0001

Data Index: 164380 (C4 (Web Text))

Max Activating Token Index: 935

Text #15

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.0136. Min Act: -0.0001

Data Index: 877959 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.0693. Min Act: -0.0001

Data Index: 1005510 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1272. Min Act: -0.0001

Data Index: 754751 (C4 (Web Text))

Max Activating Token Index: 410

Text #18

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1265378 (C4 (Web Text))

Max Activating Token Index: 837

Text #19

Max Range: 1.5351. Min Range: -1.5351

Max Act: 1.3990. Min Act: -0.0001

Data Index: 548849 (C4 (Web Text))

Max Activating Token Index: 620